跳到正文
cccskills
免费在 GitHub 公开

sync-modules

Cerate or Update a GitHub Issue for each Module in the task document.

中文简介正在准备中。当前显示原文说明。

集成工具GitHub
查看安装方法

包含的文件(1)

  • SKILL.md2.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Outline

  1. Locate Feature & Tasks:

    • Extract the feature name from the branch name or user input like ###-feature-name, e.g., 001-feature-name.
    • Find the most likely feature in the specs directory, i.e., ./specs/[###-feature-name]. The feature id and name must be exact match.
    • The feature spec must has a task directory (i.e, tasks/) including a metadata.md file and multiple module_i.md files. All paths must be absolute.
    • Find the feature issue link in the tasks/metadata.md file. If not exists, search the feature issue on the GitHub by the prefix [###-feature-name]. The feature id and name must be exact match. If not found, stop and report error "Feature issue not found: [###-feature-name]".
  2. Check Current Modules:

    • View the feature issue and its sub-issues on the GitHub to confirm the current modules.
    • If some modules are missing, go to Step 3 to create them.
    • If some modules are modified (local files and remote issues are different), synchronize them.
  3. Create Module Issue: (For each module_i.md file)

    • Create a new issue on the GitHub.
    • The issue title is [###-feature-name] Module <i>: <description>, e.g., [001-add-frontend] Module 1: Setup for biagent.
    • The body is the Goal (at the beginning of the module_i.md file) and tasks list (at metadata.md) of the module.
    • The Assignee is given in the module_i.md file. @me by default.
    • The Labels are given in the module_i.md file.
    • The Milestone is given in the module_i.md file. Skip if None is given.
    • The Project is given in the module_i.md file. Skip if None is given.
  4. Link Sub-issue (Use GitHub Sub-issue api):

    • Set each Module Issue as the sub-issue of the Feature Issue.
    • First find the issueId.
    • Then link the sub-issue using the following commands:
      gh api graphql -f query='mutation { addSubIssue(input: {issueId: "xxx", subIssueId: "xxx"}) { issue { id title } subIssue { id title } } }'
      

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

codegraph

免费

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection, auto-merge candidates, labeling). Also covers creating, inspecting, and repairing a CodeScope index. Use for: code structure, who calls what, why something changed, similar functions, module boundaries, bug tracing, class relationships, PR risk/conflicts, or any question benefiting from a code knowledge graph. Applies when a `.codegraph` index exists in the workspace, or when the user wants to create one.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1712026年10月22日 更新

Submit a new issue to the project.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1712026年10月22日 更新

create-pr

免费

Submit a new Pull Request to the project.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1712026年10月22日 更新

Analyze new commits and generate related test cases.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1712026年10月22日 更新

Vulnerability audit and dataflow analysis built on the neug CPG engine. file_audit (default, recommended): first builds a function-level summary graph (tier1) over the entire project, then incrementally builds detailed CPGs (tier2) on demand for chosen functions; both tiers coexist in a single neug database (unified schema, cross-layer refines edges; C/Java/Python/Rust). All capabilities are exposed as CLI tool subcommands (audit/overview/build/query/methods/paths), so an agent can drive the audit step by step via shell; the audit subcommand can also run the built-in LLM loop. The same tooling also supports a dataflow analysis mode (Workflow C): no vulnerability hunting, only variable-level dataflow tracing for functions of interest, producing dataflow_analysis.json. repo_audit: multi-round LLM/Cypher audit over a full-repo CPG. Use when the user asks to audit a codebase/project for vulnerabilities, scan a project with CPG/neug, run repo_audit/file_audit, find source-to-sink taint paths, or analyze dataflow inside a function. Supports C, Java, Python, and Rust.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1712026年10月22日 更新

Execute the implementation planning workflow using the plan template to generate design artifacts.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1712026年10月22日 更新

查看 alibaba 的全部技能

报告此技能的问题